|本期目录/Table of Contents|

[1]张欣怡,戴成元,李微雨,等.基于TPE-XGBoost算法的再生粗骨料混凝土抗压强度预测模型[J].建筑科学与工程学报,2024,41(06):100-110.[doi:10.19815/j.jace.2022.10013]
　ZHANG Xinyi,DAI Chengyuan,LI Weiyu,et al.Prediction model of compressive strength of recycled coarse aggregate concrete based on TPE-XGBoost algorithm[J].Journal of Architecture and Civil Engineering,2024,41(06):100-110.[doi:10.19815/j.jace.2022.10013]
点击复制

基于TPE-XGBoost算法的再生粗骨料混凝土抗压强度预测模型(PDF)
分享到：

《建筑科学与工程学报》[ISSN:1673-2049/CN:61-1442/TU]

卷:
41卷
期数:
2024年06期
页码:
100-110
栏目:
建筑材料
出版日期:
2024-11-30

文章信息/Info

Title:
Prediction model of compressive strength of recycled coarse aggregate concrete based on TPE-XGBoost algorithm
文章编号:
1673-2049(2024)06-0100-11
作者:
张欣怡1,戴成元1,2,李微雨1,陈 阳1,刘 兵1
(1. 桂林理工大学 土木工程学院,广西 桂林 541004; 2. 桂林理工大学 广西建筑新能源与节能重点实验室,广西 桂林 541004)
Author(s):
ZHANG Xinyi1, DAI Chengyuan1,2, LI Weiyu1, CHEN Yang1, LIU Bing1
(1. School of Civil Engineering, Guilin University of Technology, Guilin 541004, Guangxi, China; 2. Guangxi Key Laboratory of New Energy and Building Energy Saving, Guilin University of Technology, Guilin 541004, Guangxi, China)
关键词:
XGBoost算法;  再生粗骨料混凝土;  抗压强度;  贝叶斯优化
Keywords:
XGBoost algorithm;  recycled coarse aggregate concrete;  compressive strength;  Bayesian optimization
分类号:
TU502
DOI:
10.19815/j.jace.2022.10013
文献标志码:
A
摘要:
为了更好地预测再生粗骨料混凝土的抗压强度,提出了基于极限提升树(XGBoost)算法的再生粗骨料混凝土抗压强度预测模型; 利用再生粗骨料混凝土数据库,对数据进行预处理,利用树结构概率密度估计贝叶斯优化(TPE-BO)方法优化模型参数; 通过实例对再生粗骨料混凝土抗压强度预测模型进行对比验证。结果表明:数据预处理和TPE-BO超参数优化方法均能在一定程度提升模型性能; 与随机森林、K邻近回归、支持向量机回归、梯度提升决策树模型相比,提出的模型有更高的预测精度和泛化能力; 高性能抗压强度预测模型可为再生粗骨料混凝土的研究和实践提供依据,同时也为再生混凝土性能预测提供新途径。
Abstract:
In order to better predict the compressive strength of recycled coarse aggregate concrete, a compressive strength prediction model for recycled coarse aggregate concrete based on extreme gradient boosting(XGBoost)algorithm was proposed. Taking the recycled coarse aggregate concrete database as the research data set, the data set was preprocessed, and the Bayesian optimization(BO)method was used to estimate the tree-structured parzen estimator(TPE)to optimize the model parameters. The comparative verification of compressive strength prediction models for recycled coarse aggregate concrete was carried out through examples. The results show that data preprocessing and TPE-BO hyperparameter optimization methods can both improve model performance to a certain extent. Compared with random forest, K-nearest neighbor regression, support vector machine regression, and gradient boosting decision tree models, the proposed model has higher prediction accuracy and generalization ability. The high performance compressive strength prediction model provides a basis for the research and practice of recycled coarse aggregate concrete, and also provides a new approach for predicting the performance of recycled concrete.

参考文献/References:

[1] 肖建庄,张航华,唐宇翔,等.废弃混凝土再生原理与再生混凝土基本问题[J].科学通报,2023,68(5):510-523.
XIAO Jianzhuang,ZHANG Hanghua,TANG Yu-xiang,et al.Principles for waste concrete recycling and basic problems of recycled concrete[J].Chinese Science Bulletin,2023,68(5):510-523.
[2]XIAO J Z.Recycled aggregate concrete[M]//Recycled Aggregate Concrete Structures.Berlin:Springer,2018:65-98.
[3]李佳彬,肖建庄,孙振平.再生粗骨料特性及其对再生混凝土性能的影响[J].建筑材料学报,2004,7(4):390-395.
LI Jiabin,XIAO Jianzhuang,SUN Zhenping,Properties of recycled coarse aggregate and its influence on recycled concrete[J].Journal of Building Materials,2004,7(4):390-395.
[4]KISKU N,JOSHI H,ANSARI M,et al.A critical review and assessment for usage of recycled aggregate as sustainable construction material[J].Construction and Building Materials,2017,131:721-740.
[5]徐 蔚.再生粗骨料取代率对混凝土基本性能的影响[J].混凝土,2006(9):45-47.
XU Wei.Experimental study on influence of recycled coarse aggregates contents on properties of recycled aggregate concrete[J].Concrete,2006(9):45-47.
[6]胡敏萍.不同取代率再生粗骨料混凝土的力学性能[J].混凝土,2007(2):52-54.
HU Minping.Mechanical properties of concrete prepared with different recycled coarse aggregates replacement rate[J].Concrete,2007(2):52-54.
[7]曾 力,赵 伟.再生粗骨料混凝土强度公式研究[J].混凝土,2009(5):80-82.
ZENG Li,ZHAO Wei.Strength formula of recycled coarse aggregate concrete[J].Concrete,2009(5):80-82.
[8]彭立港,赵羽习,曾维来,等.再生粗骨料混凝土界面参数研究[J].建筑材料学报,2022,25(7):737-743.
PENG Ligang,ZHAO Yuxi,ZENG Weilai,et al.Interface parameter of recycled coarse aggregate concrete[J].Journal of Building Materials,2022,25(7):737-743.
[9]李秋义,岳公冰,郭远新.再生混凝土性能调控与配合比设计[M].北京:中国建筑工业出版社,2019.
LI Qiuyi,YUE Gongbing,GUO Yuanxin.Property regulation and mix proportion design of recycled concrete[M].Beijing:China Architecture & Building Press,2019.
[10]王 伟,周爱兆,冯 丽,等.再生粗骨料混凝土抗压强度-龄期数学模型[J].建筑材料学报,2012,15(5):633-637.
WANG Wei,ZHOU Aizhao,FENG Li,et al.Mathematical model for age-dependent compressive strength of recycled coarse aggregate concrete[J].Journal of Building Materials,2012,15(5):633-637.
[11]李马力,隋莉莉,周英武,等.再生粗骨料混凝土强度预测模型研究[J].防灾减灾工程学报,2016,36(1):132-137.
LI Mali,SUI Lili,ZHOU Yingwu,et al.Study of strength model for recycled coarse aggregate concrete[J].Journal of Disaster Prevention and Mitigation Engineering,2016,36(1):132-137.
[12]韩 越,张新东.再生混凝土强度预测的神经网络模型[J].混凝土,2008(4):22-23,26.
HAN Yue,ZHANG Xindong.Neural network model of the recycled concrete strength[J].Concrete,2008(4):22-23,26.
[13]DUAN Z H,POON C S,XIAO J Z.Using artificial neural networks to assess the applicability of recycled aggregate classification by different specifications[J].Materials and Structures,2016,50(2):107.
[14]黄 炜,周 烺,葛 培,等.基于PSO-BP和GA-BP神经网络再生砖骨料混凝土强度模型的对比研究[J].材料导报,2021,35(15):15026-15030.
HUANG Wei,ZHOU Lang,GE Pei,et al.A comparative study on compressive strength model of recycled brick aggregate concrete based on PSO-BP and GA-BP neural networks[J].Materials Reports,2021,35(15):15026-15030.
[15]CHEN T,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//KRISHNAPURAM B,SHAH M.Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining.New York:ACM,2016:785-794.
[16]林光伟,王 珊,张西亚,等.基于贝叶斯参数优化的无模型自适应硅单晶直径控制[J].人工晶体学报,2022,51(2):229-241,247.
LIN Guangwei,WANG Shan,ZHANG Xiya,et al.Model-free adaptive diameter control of monocrystalline silicon based on Bayesian parameter optimization[J].Journal of Synthetic Crystals,2022,51(2):229-241,247.
[17]史才军,曹芷杰,谢昭彬.再生混凝土力学性能的研究进展[J].材料导报,2016,30(23):96-103,127.
SHI Caijun,CAO Zhijie,XIE Zhaobin.Research progress in the mechanical properties of recycled aggregate concrete[J].Materials Reports,2016,30(23):96-103,127.
[18]孙 晨,文 龙,李新宇,等.基于自动机器学习的不平衡故障诊断方法[J].计算机集成制造系统,2021,27(10):2837-2847.
SUN Chen,WEN Long,LI Xinyu,et al.New automated machine learning based imbalanced learning method for fault diagnosis[J].Computer Integrated Manufacturing Systems,2021,27(10):2837-2847.
[19]ZOU M,JIANG W G,QIN Q H,et al.Optimized XGBoost model with small dataset for predicting relative density of Ti-6Al-4V parts manufactured by selective laser melting[J].Materials,2022,15(15):5298.
[20]武梦婷,陈秋松,齐冲冲.基于机器学习的边坡安全稳定性评价及防护措施[J].工程科学学报,2022,44(2):180-188.
WU Mengting,CHEN Qiusong,QI Chongchong.Slope safety,stability evaluation,and protective measures based on machine learning[J].Chinese Journal of Engineering,2022,44(2):180-188.
[21]陈宗平,占东辉,徐金俊.再生粗骨料含量对再生混凝土力学性能的影响分析[J].工业建筑,2015,45(1):130-135.
CHEN Zongping,ZHAN Donghui,XU Jinjun.Research on mechanical properties of recycled concrete using different recycled coarse aggregate replacement[J].Industrial Construction,2015,45(1):130-135.
[22]张丽素,乔京生,张 弛,等.不同因素对再生混凝土抗压强度的影响[J].华北理工大学学报(自然科学版),2018,40(2):61-65.
ZHANG Lisu,QIAO Jingsheng,ZHANG Chi,et al.Effect of different factors on compressive strength of recycled concrete[J].Journal of North China University of Science and Technology(Natural Science Edition),2018,40(2):61-65.
[23]郭远新,李秋义,汪卫琴,等.再生粗骨料品质提升技术研究[J].混凝土,2015(6):134-138.
GUO Yuanxin,LI Qiuyi,WANG Weiqin,et al.Research on recycled coarse aggregate quality of enhancement technology[J].Concrete,2015(6):134-138.

相似文献/References:

[1]沙 蒙,李 祥,刘紫洋,等.方钢管石灰石机制砂再生粗骨料混凝土黏结滑移本构模型[J].建筑科学与工程学报,2023,40(01):38.[doi:10.19815/j.jace.2021.08025]
　SHA Meng,LI Xiang,LIU Ziyang,et al.Bond-slip constitutive model of recycled coarse aggregate concrete with limestone manufactured sand in square steel tubes[J].Journal of Architecture and Civil Engineering,2023,40(06):38.[doi:10.19815/j.jace.2021.08025]

备注/Memo

备注/Memo:
收稿日期:2023-11-07
基金项目:国家自然科学基金项目(52108201); 广西自然科学基金项目(2021GXNSFBA220049); 广西建筑新能源与节能重点实验室基金项目(桂科能22-J-21-28)
通信作者:戴成元(1974-),男,副教授,E-mail:dcy366@126.com。
Author resume: DAI Chengyuan(1974-),male,associate professor,E-mail:dcy366@126.com.
更新日期/Last Update: 2024-12-10